What are the hardware requirements for WeVisCut?

WeVisCut requires approximately 18.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed WeVisCut and how large is it?

WeVisCut is developed by tencent, a model with 9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate WeVisCut?

WeVisCut is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

WeVisCut by tencent — VRAM 18.8GB

Name: WeVisCut
Author: tencent

WeVisCut is an open-source language model by tencent. Features: 9b LLM, VRAM: 18.8GB, License: other, LLM Explorer Score: 0.28.

Arxiv:2610.38352 Agent Any-to-any Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-9b Endpoints compatible Image-text-to-text Long-horizon Qwen3.5 Qwen3 5 Region:us Safetensors Tool-use Video-editing

Model Card on HF 🤗: https://huggingface.co/tencent/WeVisCut

WeVisCut Parameters and Internals

LLM Name	WeVisCut
Repository 🤗	https://huggingface.co/tencent/WeVisCut
Base Model(s)	Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B
Model Size	9b
Required VRAM	18.8 GB
Updated	2026-11-01
Maintainer	tencent
Model Type	qwen3_5
Model Files	18.8 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	5.15.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the WeVisCut capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to WeVisCut

Best Alternatives	Context / RAM	Downloads	Likes
HYZ 01 9B	256K / 18.8 GB	102	1
Clef Flash	0K / 18.8 GB	36817	853
Qwen3.5 9B	0K / 19.3 GB	12207758	1799
Qwable 9B Claude Fable 5	0K / 18.8 GB	1088	115
Ornith 1.0 9B	0K / 18.8 GB	800231	566
MiMo V2.6 Distill Qwen 9B	0K / 18.8 GB	5705	429
Qwythos 9B Claude Mythos 5 1M	0K / 18.8 GB	37427	906
Elephant 1	0K / 18.8 GB	1344	75
Flux 3 Image Klein Pup	0K / 18.8 GB	6948	54
LensVLM 9B	0K / 18.8 GB	1840	258

Note: green Score (e.g. "73.2") means that the model is better than tencent/WeVisCut.